© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6991
    Prev
    Next
    INDEX
    Explanations

    mentions of software updates and system security measures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    1.1%
    1967
    +0.14
    0.8%
    1343
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1909
    +0.20
    0.10
    1343
    +0.14
    0.12
    757
    +0.11
    0.11
    Negative Logits
    <bos>
    -3.33
    ⓧ
    -1.07
    OGND
    -0.89
    rungsseite
    -0.87
     censiti
    -0.85
    
    -0.81
    RTLR
    -0.81
    sizeCache
    -0.81
    abetes
    -0.79
    GEBURTSDATUM
    -0.77
    POSITIVE LOGITS
     practition
    1.57
     emphat
    1.56
     increa
    1.53
     affor
    1.52
     inev
    1.49
     volunte
    1.46
     maneu
    1.46
     accla
    1.44
     disagre
    1.43
     reluct
    1.42
    Activations Density 0.569%

    No Known Activations